Project Directors: Thomas Keenan, Natalia Ermolaev, Andrew Janco (UPenn)
The Pages of Early Soviet Performance (PESP) uses machine learning to generate multiple datasets of early-Soviet illustrated periodicals related to the performing arts. By using computer vision techniques and training a YOLO (You Only Look Once) real-time object detection model, we are producing textual and image data that will facilitate new avenues of research about Soviet culture during the first decades after the October Revolution (1917-1932). The dataset is published here.
New Languages for NLP: Building Linguistic Diversity in the Digital Humanities
This workshop series, funded by a National Endowment for Humanities Institute for Advanced Topics in the Digital Humanities grant, ran between June 2021 and May 2022. Participants learned to annotate linguistic data and train statistical language models for under-resourced languages. One of the teams worked on Dostoevsky’s Russian. Training material will soon be available on DARIAH Campus.
Playing Soviet: The Visual Language of Early Soviet Children’s Books project
Project Directors: Kat Reischl and Thomas Keenan
This interactive database of children’s book illustrations draws the little-known and rarely-seen Soviet children’s books from the Cotsen Collection at Princeton’s Firestone Library. The featured illustrations have been selected and annotated by a diverse group of scholars and students of Russian and Soviet culture. The site’s customizable data visualizations, still under construction, will map relationships among artists, image types, color, style, and publication information.
The Serge Prokofiev Archive as Data
Project Directors: Natalia Ermolaev and Mark Saccomano (Columbia University)
This project explores ways that DH methods and tools can transform our engagement with archival collections. Based on the robust material of the Serge Prokofiev Archive at Columbia University, this project is part data curation, part data transformation, part data analysis and part data storytelling.
Soviet Journals Reconnected: Periodical Networks under Late Socialism
Project Director: Philip Gleissner
Soviet Journals Reconnected is a database of bibliographical metadata related to the “thick journals,” or monthlies dedicated to literature, art, society, and politics, that were a cornerstone of Soviet culture. In the 1960s and 1970s, their readership was in the millions; thousands of authors were published on their pages. Soviet Journals Reconnected explores the rich life of these periodicals through their bibliographical data. It traces the work of editorial offices, development of themes and genres in the journals, and the emergence of segmented communities of authors around them.
You must be logged in to post a comment.